{"total":60,"rows":[{"id":"2109.05322","title":"Latent Hatred: A Benchmark for Understanding Implicit Hate Speech","created":"2021-09-11","cited_by_count":217,"area":null},{"id":"2102.00086","title":"Challenges in Automated Debiasing for Toxic Language Detection","created":"2021-01-29","cited_by_count":96,"area":null},{"id":"2109.05184","title":"MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets","created":"2021-09-11","cited_by_count":86,"area":null},{"id":"2108.03362","title":"On Measures of Biases and Harms in NLP","created":"2021-08-07","cited_by_count":81,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2107.03451","title":"Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling","created":"2021-07-07","cited_by_count":78,"area":null},{"id":"2106.11410","title":"A Survey of Race, Racism, and Anti-Racism in NLP","created":"2021-06-21","cited_by_count":75,"area":null},{"id":"2102.08886","title":"Towards generalisable hate speech detection: a review on obstacles and solutions","created":"2021-02-17","cited_by_count":66,"area":null},{"id":"2202.00126","title":"Handling Bias in Toxic Speech Detection: A Survey","created":"2022-01-26","cited_by_count":61,"area":null},{"id":"2102.04257","title":"Fairness for Unobserved Characteristics: Insights from Technological Impacts on Queer Communities","created":"2021-02-03","cited_by_count":40,"area":null},{"id":"2211.03433","title":"Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering","created":"2022-11-07","cited_by_count":40,"area":null},{"id":"2305.14291","title":"Evaluation of African American Language Bias in Natural Language Generation","created":"2023-05-23","cited_by_count":36,"area":null},{"id":"2204.01440","title":"Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study","created":"2022-04-04","cited_by_count":30,"area":null},{"id":"2103.10282","title":"Modeling the Second Player in Distributionally Robust Optimization","created":"2021-03-18","cited_by_count":29,"area":null},{"id":"2204.01734","title":"On Explaining Multimodal Hateful Meme Detection Models","created":"2022-04-04","cited_by_count":29,"area":null},{"id":"2106.03783","title":"An Information-theoretic Approach to Distribution Shifts","created":"2021-06-07","cited_by_count":25,"area":null},{"id":"2302.06321","title":"Parameter-efficient Modularised Bias Mitigation via AdapterFusion","created":"2023-02-13","cited_by_count":25,"area":null},{"id":"2402.00371","title":"What Does the Bot Say? Opportunities and Risks of Large Language Models in Social Media Bot Detection","created":"2024-02-01","cited_by_count":25,"area":null},{"id":"2109.13137","title":"Mitigating Racial Biases in Toxic Language Detection with an Equity-Based Ensemble Framework","created":"2021-09-27","cited_by_count":19,"area":null},{"id":"2205.15171","title":"Modular and On-demand Bias Mitigation with Attribute-Removal Subnetworks","created":"2022-05-30","cited_by_count":18,"area":null},{"id":"2210.07455","title":"Controlling Bias Exposure for Fair Interpretable Predictions","created":"2022-10-14","cited_by_count":18,"area":null},{"id":"2503.01623","title":"Lost in Moderation: How Commercial Content Moderation APIs Over- and Under-Moderate Group-Targeted Hate Speech and Linguistic Variations","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2109.02941","title":"Countering Online Hate Speech: An NLP Perspective","created":"2021-09-07","cited_by_count":12,"area":null},{"id":"2110.14839","title":"Hate Speech Classifiers Learn Human-Like Social Stereotypes","created":"2021-10-28","cited_by_count":12,"area":null},{"id":"2210.11762","title":"Detecting Unintended Social Bias in Toxic Language Datasets","created":"2022-10-21","cited_by_count":12,"area":null},{"id":"2103.01328","title":"ToxCCIn: Toxic Content Classification with Interpretability","created":"2021-03-01","cited_by_count":10,"area":null},{"id":"2410.13281","title":"BanTH: A Multi-label Hate Speech Detection Dataset for Transliterated Bangla","created":"2024-10-17","cited_by_count":10,"area":null},{"id":"2102.03671","title":"From Toxicity in Online Comments to Incivility in American News: Proceed with Caution","created":"2021-02-06","cited_by_count":8,"area":null},{"id":"2202.13056","title":"Automated Identification of Toxic Code Reviews Using ToxiCR","created":"2022-02-26","cited_by_count":8,"area":null},{"id":"2203.10675","title":"Mitigating Gender Bias in Machine Translation through Adversarial Learning","created":"2022-03-20","cited_by_count":8,"area":null},{"id":"2207.10032","title":"Detecting Harmful Online Conversational Content towards LGBTQIA+ Individuals","created":"2022-06-15","cited_by_count":8,"area":null},{"id":"2211.02882","title":"HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Models","created":"2022-11-05","cited_by_count":8,"area":null},{"id":"2106.07240","title":"Mitigating Biases in Toxic Language Detection through Invariant Rationalization","created":"2021-06-14","cited_by_count":7,"area":null},{"id":"2205.06621","title":"Analyzing Hate Speech Data along Racial, Gender and Intersectional Axes","created":"2022-05-13","cited_by_count":7,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2103.05345","title":"Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company's Reputation","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2111.04260","title":"Personalized Benchmarking with the Ludwig Benchmarking Toolkit","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2205.12391","title":"Toward Understanding Bias Correlations for Mitigation in NLP","created":"2022-05-24","cited_by_count":5,"area":null},{"id":"2110.13980","title":"Adversarial Attacks and Defenses for Social Network Text Processing Applications: Techniques, Challenges and Future Research Directions","created":"2021-10-26","cited_by_count":4,"area":null},{"id":"2212.07877","title":"Manifestations of Xenophobia in AI Systems","created":"2022-12-15","cited_by_count":4,"area":null},{"id":"2204.07661","title":"Finding Pareto Trade-offs in Fair and Accurate Detection of Toxic Speech","created":"2022-04-15","cited_by_count":3,"area":null},{"id":"2206.08445","title":"Enriching Abusive Language Detection with Community Context","created":"2022-06-16","cited_by_count":3,"area":null},{"id":"2206.08978","title":"Towards a Deep Multi-layered Dialectal Language Analysis: A Case Study of African-American English","created":"2022-06-03","cited_by_count":3,"area":null},{"id":"2212.03747","title":"Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Review","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2311.09428","title":"Beyond Detection: Unveiling Fairness Vulnerabilities in Abusive Language Models","created":"2023-11-15","cited_by_count":3,"area":null},{"id":"2503.10789","title":"Data Caricatures: On the Representation of African American Language in Pretraining Corpora","created":"2025-03-13","cited_by_count":3,"area":null},{"id":"2204.07010","title":"Anti-Asian Hate Speech Detection via Data Augmented Semantic Relation Inference","created":"2022-04-14","cited_by_count":2,"area":null},{"id":"2406.17793","title":"Deep Learning Approaches for Detecting Adversarial Cyberbullying and Hate Speech in Social Networks","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2505.24538","title":"Don't Erase, Inform! Detecting and Contextualizing Harmful Language in Cultural Heritage Collections","created":"2025-05-30","cited_by_count":2,"area":null},{"id":"2106.02810","title":"An Attribute-Aligned Strategy for Learning Speech Representation","created":"2021-06-05","cited_by_count":1,"area":null},{"id":"2112.09326","title":"Cinderella's shoe won't fit Soundarya: An audit of facial processing tools on Indian faces","created":"2021-12-17","cited_by_count":1,"area":null},{"id":"2203.02392","title":"Beyond Plain Toxic: Detection of Inappropriate Statements on Flammable Topics for the Russian Language","created":"2022-03-04","cited_by_count":1,"area":null},{"id":"2406.09977","title":"Disentangling Dialect from Social Bias via Multitask Learning to Improve Fairness","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2407.11933","title":"Fairness-Aware Multi-Group Target Detection in Online Discussion","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2505.19528","title":"AmpleHate: Amplifying the Attention for Versatile Implicit Hate Detection","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2108.06487","title":"Investigating Bias In Automatic Toxic Comment Detection: An Empirical Study","created":"2021-08-14","cited_by_count":0,"area":null},{"id":"2203.11401","title":"Suum Cuique: Studying Bias in Taboo Detection with a Community Perspective","created":"2022-03-22","cited_by_count":0,"area":null},{"id":"2505.02252","title":"Personalisation or Prejudice? Addressing Geographic Bias in Hate Speech Detection using Debias Tuning in Large Language Models","created":"2025-05-04","cited_by_count":0,"area":null},{"id":"2604.14970","title":"Explain the Flag: Contextualizing Hate Speech Beyond Censorship","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2609.11067","title":"When Noise Fabricates Bias: The Fragility of LLM-as-a-Judge Bias Measurement under Noisy Text","created":"2026-09-10","cited_by_count":0,"area":null}],"next_cursor":null}